Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3736 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4877. Min Act: -0.1700
Data Index: 364423 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4877. Min Act: -0.1683
Data Index: 5502643 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4965. Min Act: -0.1700
Data Index: 3771797 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4789. Min Act: -0.1598
Data Index: 6250358 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4701. Min Act: -0.1700
Data Index: 5721153 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4526. Min Act: -0.1698
Data Index: 6250364 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4614. Min Act: -0.1700
Data Index: 4665785 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4614. Min Act: -0.1699
Data Index: 6593924 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4526. Min Act: -0.1700
Data Index: 752959 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4614. Min Act: -0.1700
Data Index: 7554688 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4526. Min Act: -0.1700
Data Index: 1923402 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4614. Min Act: -0.1700
Data Index: 4452378 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4438. Min Act: -0.1698
Data Index: 1807133 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4438. Min Act: -0.1700
Data Index: 2972955 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4438. Min Act: -0.1700
Data Index: 2361222 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4438. Min Act: -0.1700
Data Index: 5895977 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4438. Min Act: -0.1700
Data Index: 2382024 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4350. Min Act: -0.1699
Data Index: 1054453 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4350. Min Act: -0.1699
Data Index: 607630 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4965. Min Range: -1.4965
Max Act: 1.4438. Min Act: -0.1700
Data Index: 5777941 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19